mlsanityData to 7 Oct 2026

Measuring Fairness in Generative Models

arXiv 2107.07754 ↗First posted 16 Jul 2021cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

Deep generative models have made much progress in improving training stability and quality of generated data. Recently there has been increased interest in the fairness of deep-generated data. Fairness is important in many applications, e.g. law enforcement, as biases will affect efficacy. Central to fair data generation are the fairness metrics for the assessment and evaluation of different generative models. In this paper, we first review fairness metrics proposed in previous works and highlight potential weaknesses. We then discuss a performance benchmark framework along with the assessment of alternative metrics.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 18 of its 22 references that are in the map. First posted on arXiv 16 Jul 2021.

Builds on

18 of 22 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  9. 2014Certifying and removing disparate impactcited by 715
  10. 2020Fairness in Machine Learning: A Surveycited by 369
  11. 2016Unrolled Generative Adversarial Networkscited by 208
  12. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
6 more
  1. 2019Fair Generative Modeling via Weak Supervisioncited by 114
  2. 2019Bias Correction of Learned Generative Models using Likelihood-Free Importance Weightingcited by 70
  3. 2021A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detectioncited by 68
  4. 2020Improving the Fairness of Deep Generative Models without Retrainingcited by 46
  5. 2018Dist-GAN: An Improved GAN using Distance Constraintscited by 26
  6. 2019Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Gamecited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 7; 2024: 9; 2025: 7; 2026: 6.

31 papers.

Sort:

By area:

  1. 2023Debiasing Vision-Language Models via Biased Promptscited by 147
  2. 2024Large-scale Reinforcement Learning for Diffusion Modelscited by 78
  3. 2023Spawrious: A Benchmark for Fine Control of Spurious Correlation Biasescited by 41
  4. 2024AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmarkcited by 28
  5. 2023Survey of Social Bias in Vision-Language Modelscited by 26
  6. 2022Discovering Transferable Forensic Features for CNN-generated Images Detectioncited by 24
  7. 2023Label-Only Model Inversion Attacks via Knowledge Transfercited by 21
  8. 2024SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIPcited by 19
  9. 2023EHRDiff: Exploring Realistic EHR Synthesis with Diffusion Modelscited by 18
  10. 2025Exploring Bias in over 100 Text-to-Image Generative Modelscited by 9
  11. 2023On Measuring Fairness in Generative Modelscited by 8
  12. 2024FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generationcited by 7
19 more
  1. 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Modelscited by 6
  2. 2025Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliancecited by 5
  3. 2025Fit for Purpose? Deepfake Detection in the Real Worldcited by 4
  4. 2024A Comprehensive Survey and Classification of Evaluation Criteria for Trustworthy Artificial Intelligencecited by 3
  5. 2024Data Pruning in Generative Diffusion Modelscited by 3
  6. 2025Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Modelscited by 3
  7. 2022Fairness in generative modelingcited by 2
  8. 2024On the Fairness, Diversity and Reliability of Text-to-Image Generative Modelscited by 2
  9. 2025On Optimal Steering to Achieve Exact Fairnesscited by 2
  10. 2024AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generationcited by 1
  11. 2026Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Modelscited by 1
  12. 2026HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasingcited by 1
  13. 2023Fair GANs through model rebalancing for extremely imbalanced class distributionscited by 0
  14. 2024Text-to-Image Representativity Fairness Evaluation Frameworkcited by 0
  15. 2025Improving Fairness in LLMs Through Testing-Time Adversariescited by 0
  16. 2026Fairness risk and its privacy-enabled solution in AI-driven robotic applicationscited by 0
  17. 2026Disparate Impact in Synthetic Data Generationcited by 0
  18. 2026Position: Fairness Failure in Generative Models is an Evaluation Problemcited by 0
  19. 2026Debias Anything: Fairness with Diversity without Supervision in Diffusion Modelscited by 0